Quantifying Confidence in Assurance 2.0 Arguments

2026-04-02T08:51:56Za94773346b61ded445042ec0977764ed47f7342d18c601208749915336390f25
CIEA-debtFrechet-boundsLLMsRAGagent-architecturesarchitecture-metamodelassurance-2.0assurance-casesautomatic-program-repaircode-repairenergy-efficiencyenergy-footprintenterprise-architecture-debtenterprise-automationenvironmental-MLfault-localizationgenerative-AIlarge-language-modelsmicroservicesperformance-regressionpractitioner-studyprobabilistic-confidencerisk-aware-batchingterminal-agents

What happened

Collection of recent CS-SE arXiv postings (Apr 2, 2026) covering methods and empirical studies across software engineering and AI-driven systems. Key contributions include: a probabilistic method to quantify confidence in Assurance 2.0 arguments; LLM-based detection of Enterprise Architecture Debt from unstructured documentation; measurement and analysis of inference-time energy footprints for domain-specific RAG vs generic LLM workflows; advocacy and evaluation of terminal-only coding agents for enterprise automation; empirical study of how microservice topology affects performance and energy

Why it matters

A reviewed impact interpretation has not been published for this record.

Evidence and limitations

Source ID
arxiv_cs_se
Record identifier
a94773346b61ded445042ec0977764ed47f7342d18c601208749915336390f25
Enrichment time
2026-04-02T08:51:56Z
AI-assisted enrichment
Yes

This record may overlap with other records. Its enrichment can be incomplete or wrong, and machine assistance was used. Validate consequential decisions against the linked source and your own environment.